Grounded Adaptation for Zero-shot Executable Semantic Parsing

2020-09-16 · EMNLP 2020 11 · Victor Zhong, Mike Lewis, Sida I. Wang, Luke Zettlemoyer

We propose Grounded Adaptation for Zero-shot Executable Semantic Parsing (GAZP) to adapt an existing semantic parser to new environments (e.g. new database schemas). GAZP combines a forward semantic parser with a backward utterance generator to synthesize data (e.g. utterances and SQL queries) in the new environment, then selects cycle-consistent examples to adapt the parser. Unlike data-augmentation, which typically synthesizes unverified examples in the training environment, GAZP synthesizes examples in the new environment whose input-output consistency are verified. On the Spider, Sparc, and CoSQL zero-shot semantic parsing tasks, GAZP improves logical form and execution accuracy of the baseline parser. Our analyses show that GAZP outperforms data-augmentation in the training environment, performance increases with the amount of GAZP-synthesized data, and cycle-consistency is central to successful adaptation.

📄 PDF Abstract BibTeX arXiv:2009.07396

Code (1)

vzhong/gazp pytorch

Tasks

Data Augmentation Dialogue State Tracking Semantic Parsing Text-To-SQL

ACE: Agentic Control for Embodied Manipulation via Zero-shot Workflow Reasoning

2026-07-05 · Iok Tong Lei, QianZhi Li, Ying Jie Yap, Yujie Zhang 외 arxiv

Open-ended tabletop manipulation requires agents to not only understand natural language but also adapt to dynamic environments and execution failures. We present ACE (Agentic Control for Embodied Manipulation), a zero-s…

Zero-shot Generalization Visual Grounding

Semantically Grounded Visual Embeddings for Zero-Shot Learning

2022-01-03 · Shah Nawaz, Jacopo Cavazza, Alessio Del Bue

Zero-shot learning methods rely on fixed visual and semantic embeddings, extracted from independent vision and language models, both pre-trained for other large-scale tasks. This is a weakness of current zero-shot learni…

Zero-Shot Learning

ZSG-IAD: A Multimodal Framework for Zero-Shot Grounded Industrial Anomaly Detection

2026-04-20 · Qiuhui Chen, Jiaxiang Song, Shuai Tan, Weimin Zhong arxiv

Deep learning-based industrial anomaly detectors often behave as black boxes, making it hard to justify decisions with physically meaningful defect evidence. We propose ZSG-IAD, a multimodal vision-language framework for…

Anomaly Detection Point Clouds

ZeroDex: Zero-Shot Long-Horizon Dexterous Manipulation via Multi-View 3D-Grounded VLM Reasoning

2026-06-17 · Jisoo Kim, Sangwon Baik, Taeksoo Kim, Sungjoo Kim 외 arxiv

We present ZeroDex, a zero-shot framework for long-horizon dexterous manipulation that grounds language instructions into executable 3D task plans from calibrated multi-view RGB images. Rather than training an end-to-end…

Few-Shot Adaptation for Multimedia Semantic Indexing

2018-07-19 · Nakamasa Inoue, Koichi Shinoda

We propose a few-shot adaptation framework, which bridges zero-shot learning and supervised many-shot learning, for semantic indexing of image and video data. Few-shot adaptation provides robust parameter estimation with…

Few-Shot Learning parameter estimation Zero-Shot Learning